Skip to main content

autogen-watsonx-client

This is an autogen>=0.4 extension for watsonx client integration.

Disclaimer

  • This is a community extension for the Autogen project, specifically for the new Autogen >= 0.4 architecture. The goal is to support IBM Watsonx.ai hosted LLMs in the Autogen framework.
  • This project is still in a very early stage under development, please create issues in this github repo for bug reports.
  • This project is a personal endeavor and is not affiliated with, endorsed by, or connected to any organization/employer in any way. The views, ideas, and opinions expressed in this project are solely my own and do not reflect those of others.

Announcements

  • 2025-01-13: the version requirement on Autogen has been updated to >=0.4.1, the integration examples have been updated accordingly, see here.

Usage

Prerequisites

  • create a python environment with version 3.10 or above
  • pip install --upgrade autogen-watsonx-client
  • pip install --upgrade autogen-agentchat>=0.4.1
  • access to a watsonx.ai instance, setting up environment variables WATSONX_API_KEY, one of WATSONX_SPACE_ID or WATSONX_PROJECT_ID, optionally WATSONX_URL

code snippets

Importing dependencies:

import os

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_watsonx_client.config import WatsonxClientConfiguration
from autogen_watsonx_client.client import WatsonXChatCompletionClient

Create a watsonx client

wx_config = WatsonxClientConfiguration(
    model_id="meta-llama/llama-3-2-90b-vision-instruct",  # pick a model you have access to on wx.ai here
    api_key=os.environ.get("WATSONX_API_KEY"),
    url=os.environ.get("WATSONX_URL"),
    space_id=os.environ.get("WATSONX_SPACE_ID"),
    project_id=os.environ.get("WATSONX_PROJECT_ID"),
)

wx_client = WatsonXChatCompletionClient(**wx_config)

Define an agent using the watsonx client and register a dummy tool for querying weather

# Define a tool
async def get_weather(city: str) -> str:
    return f"The weather in {city} is 73 degrees and Sunny."


async def main() -> None:
    # Define an agent
    weather_agent = AssistantAgent(
        name="weather_agent",
        model_client=wx_client,
        tools=[get_weather],
    )

    # Define termination condition
    termination = TextMentionTermination("TERMINATE")

    # Define a team
    agent_team = RoundRobinGroupChat([weather_agent], termination_condition=termination)

    # Run the team and stream messages to the console
    stream = agent_team.run_stream(task="What is the weather in New York?")
    await Console(stream)


# NOTE: if running this inside a Python script you'll need to use asyncio.run(main()).
await main()

Refer to here for more detailed examples.

Metadata

Release files for autogen-watsonx-client 0.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for autogen-watsonx-client 0.0.5
File Size Uploaded Provenance Actions
autogen_watsonx_client-0.0.5.tar.gz 6.3 kB Without provenance Details for autogen_watsonx_client-0.0.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for autogen-watsonx-client 0.0.5
File Interpreter ABI Platform Actions
autogen_watsonx_client-0.0.5-py3-none-any.whl Python 3 none any Details for autogen_watsonx_client-0.0.5-py3-none-any.whl

Total release size: 14.1 kB

Release files / autogen_watsonx_client-0.0.5.tar.gz

Download URL autogen_watsonx_client-0.0.5.tar.gz
Size 6.3 kB
Tags Source
SHA-256 checksum
How to use checksums
8cb450345c8a734d5c3c764f824a2647a434f1ba9dfb1567e3845cccbf6204f1
BLAKE2b-256 checksum
How to use checksums
63be1d16fe9eed557afa8fe70d7516f3c94cac03703a7999c086f85e9b157442
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.11.10

Release files / autogen_watsonx_client-0.0.5-py3-none-any.whl

Download URL autogen_watsonx_client-0.0.5-py3-none-any.whl
Size 7.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e3983063e19797416e8a6b162021752e4eef8865e5afd64ac5ec2645809144b7
BLAKE2b-256 checksum
How to use checksums
2e6901750f9cd26d63410fe320a3f1a3d023a54baf6250e63742765e315a254a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.11.10

Security for autogen-watsonx-client 0.0.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page